AI providers: correlation decision and transcript correction move to OpenAI gpt-4o-mini

One funded account (OpenAI) now covers extraction, embeddings, summaries,
the ambiguous-scene correlation call and transcript correction; Groq stays
optional for STT. New app/internal/llm.py picks the provider from the model
name, so setting either model back to a gemini-* ID needs no code change.
Usage accounting for replay runs now covers both providers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

drb-c2-core/app/internal/recorrelation_sweep.py

@@ -70,13 +70,13 @@ def pipeline_worst_case_seconds(n_scenes: int = _BOUND_SCENES) -> float:
     from app.internal.transcription import stt_targets
     stt_providers = max(1, len(stt_targets()))
     stt = stt_providers * stt_rounds * openai_attempts * settings.stt_timeout_seconds
-    # Transcript correction (inside transcribe_call). gemini.generate_json only
-    # re-issues a request when the model rejects a thinking level — a fast
-    # 400, not a timeout — and google-genai itself does not retry.
-    correction = settings.gemini_timeout_seconds
+    # Transcript correction and the correlation decision go through
+    # llm.generate_json; the bound depends on which provider serves the model.
+    from app.internal import llm
+    correction = llm.timeout_seconds(settings.transcript_correction_model)
     extraction = openai_attempts * settings.openai_timeout_seconds
     embeddings = n_scenes * openai_attempts * settings.openai_timeout_seconds
-    correlation = settings.gemini_timeout_seconds  # at most one LLM call, scene 0 (#299)
+    correlation = llm.timeout_seconds(settings.corr_cheap_model)  # at most one LLM call, scene 0 (#299)
     return stt + correction + extraction + embeddings + correlation + _NON_AI_SLACK_SECONDS